R的简单实用代码记录

R的简单实用代码记录

赋值

>n<-10
>n
[1]10
#或
>20-n
>n
[1]20
#或
>assign("n",30)
>n
[1]30
#或
>n=4o
>n
[1]40

也可以直接输入函数表达式

>((10+2)*5-2^4)/4
[1]11
>sqrt(3)+exp(-2)
[1]1.867386

#代表注释开始

在线帮助

>help.start()
#关于R的基本知识的学习
>help(fun)
#或
>?fun
#显示该函数的帮助页面
>help("char")
#显示具有特殊语法意义字符的“char”帮助页面
>help("bs", try.all.packages=TRUE)
>help("bs", package="splines")
#在特定包或者全部包内搜索该函数

>apropos(fun)
或
>apropos("fun")
#找出所有名字中含有fun的函数，（只在已载入的包中），
#如果fun不是完整的函数名称，则第一条命令会出错。

>help.search("char")
#得到所有在帮助页面的含有字符char的函数，搜索范围比apropos更广泛
>find(char)
>find("char")
#得到命名为char的函数所在的程序包

>args(fun)
>args("fun")
>#得到名为fun的函数的自变量列表

R包的代码安装

>install.packages("ggplot2")
#字符串必须被双引号包围，R包的名称需要是字符串。
#同时选择dependences 是TURE（已默认）
>installed.packages()
#显示已安装R包
>install devtools

包的载入

>library(devtools)
#也可以直接点击packeages的包前的选项格。console上会显示这一代码。
>remove.packages("name")#卸载R包
>.libPaths()#路径查询
>install.github("name")#从GitHub上面下载选用该函数

生成数据序列

#向量：每个数据都有其自己的位置。（index）
#区别于集合的无序性
>identical(a,b)#使用该函数进行向量数据是否完全一致的区分。
#[]的功能：从向量中提取相应的元素。
#c:combines
#在[]中加入-就是去除相应的元素
>c(2,4,56,33)
#c函数可以combine字符串，数值串。
>c(1,2,"ABC")
[1] "1"   "2"   "ABC"

数值型向量

> vector1 <- c(1:3,6:10)
> vector1
[1]  1  2  3  6  7  8  9 10
> x <- 1
> class(x)
[1] "numeric"
> is.integer(x)
[1] FALSE
#在R中1也只被视作数值型，不视作整型

> 3/2
[1] 1.5
#数值型与整型在R中是一致的

> y <- 1:3
> class(y)
[1] "integer"
#整型的生成

seq,rep函数的调用

> seq(from = 1, to = 5, by =1 )
[1] 1 2 3 4 5
> seq(from = 1, to = 5, by =0.5 )
[1] 1.0 1.5 2.0 2.5 3.0 3.5 4.0 4.5 5.0
> seq(from = 10, to = 1, by =-1 )
 [1] 10  9  8  7  6  5  4  3  2  1
> seq(from = 10, to = 1, length.out=8 )
[1] 10.000000  8.714286  7.428571  6.142857  4.857143  3.571429  2.285714  1.000000
> seq(1,10,len=5)
[1]  1.00  3.25  5.50  7.75 10.00
> seq(1,10,along.with=5)
[1] 1
> seq(1,10,along.with=1:3)
[1]  1.0  5.5 10.0
#seq函数生成数值型向量的调用，by表示步长，length.out是分为几份。

> rep(c(1,3),times=5)
 [1] 1 3 1 3 1 3 1 3 1 3
> rep(c(1,3),each=5)
 [1] 1 1 1 1 1 3 3 3 3 3
> rep(c(1,3),len=9)
[1] 1 3 1 3 1 3 1 3 1
> x <- rep(1:2,times=4)
> length(x)
[1] 8
#rep函数的调用生成重复的数值型向量

逻辑型向量

> logit <-rep (c(TRUE,FALSE),len=5)
> sum(logit)
[1] 3
#逻辑函数的本质是数值型向量，可以用SUM函数对其求和得到无缺失的总和
> logit2 <- c(100>99,100>101)
> class(logit2)
[1] "logical"
> logit2
[1]  TRUE FALSE
> logit2 <- c(100>99,100=1)
Error:unexpected'=' in "logit2 <- c(100>99,100="
> logit2 <- c(100>99,100==1)
> logit2
[1]  TRUE FALSE
#使用两个==来进行逻辑判断
> logit4 <- c(100!=1)
> logit4
[1] TRUE
#不等于使用!=来表示
> logit4 <- c(100>90&100>110)
> logit4
[1] FALSE
> logit5<- c(100>90|100>110)
> logit5
[1] TRUE
#或与且的表示

逻辑表达式的使用

> x <- seq(1,100,length=20)
> x
 [1]   1.000000   6.210526  11.421053  16.631579
 [5]  21.842105  27.052632  32.263158  37.473684
 [9]  42.684211  47.894737  53.105263  58.315789
[13]  63.526316  68.736842  73.947368  79.157895
[17]  84.368421  89.578947  94.789474 100.000000
> index <- x>80
> index
 [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
 [9] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[17]  TRUE  TRUE  TRUE  TRUE
> x[index]
[1]  84.36842  89.57895  94.78947 100.00000
#方括号返回TRUE的值
> which(x>80)
[1] 17 18 19 20
> x[which(x>80)]
[1]  84.36842  89.57895  94.78947 100.00000
#which返回相应数值

> which(x>80&x<90)
[1] 17 18
> x[which(x>80&x<90)]
[1] 84.36842 89.57895
> x[x>80&x<90]#且
[1] 84.36842 89.57895
> x[x>80|x<90]#或
 [1]   1.000000   6.210526  11.421053  16.631579
 [5]  21.842105  27.052632  32.263158  37.473684
 [9]  42.684211  47.894737  53.105263  58.315789
[13]  63.526316  68.736842  73.947368  79.157895
[17]  84.368421  89.578947  94.789474 100.000000

字符串

> string <- c("abc","1","2")
> string
[1] "abc" "1"   "2"  
> class(string)
[1] "character"
> is.character(string)
[1] TRUE

letters&LETTERS

> letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m"
[14] "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
> LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M"
[14] "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
#更快地生成向量
> letters[1:5]
[1] "a" "b" "c" "d" "e"
> LETTERS[24:28]
[1] "X" "Y" "Z" NA  NA 
#NA：not available
> y <-1:5 
> y
[1] 1 2 3 4 5
> y[6]
[1] NA

因子型向量(分类变量)

有序/无序

> my_fac <- factor(x=rep(c(1,2),times=5),levels = c(1,2),labels = c("Male","Female"))
> my_fac
 [1] Male   Female Male   Female Male   Female Male  
 [8] Female Male   Female
Levels: Male Female
> class(my_fac)
[1] "factor"
> my_fac2 <- factor(LETTERS[1:5],labels = letters[1:5])
> my_fac2
[1] a b c d e
Levels: a b c d e
> my_fac3 <- factor(1:5,labels = letters[1:5])
> my_fac3
[1] a b c d e
Levels: a b c d e

> my_fac4 <- gl(n=2,k=5,labels = c("Control","Treatment"))
> my_fac4
 [1] Control   Control   Control   Control   Control  
 [6] Treatment Treatment Treatment Treatment Treatment
Levels: Control Treatment
#n：水平的个数，k：每个因子重复的次数。
> my_fac5 <- gl(n=2,k=1,labels = c("Control","Treatment"))
> my_fac5
[1] Control   Treatment
Levels: Control Treatment
> my_fac5 <- gl(n=2,k=1,length=8,labels = c("Control","Treatment"))
> my_fac5
[1] Control   Treatment Control   Treatment Control  
[6] Treatment Control   Treatment
Levels: Control Treatment

互相转换

> temp_string <- c("A","B","AB","O")
> my_fac6 <- as.factor(temp_string)#字符串转为因子
> my_fac6
[1] A  B  AB O 
Levels: A AB B O

> as.character(my_fac6)#因子转为字符串
[1] "A"  "B"  "AB" "O" 

> x <- 1:5
> x
[1] 1 2 3 4 5
> as.factor(x)
[1] 1 2 3 4 5
Levels: 1 2 3 4 5
> as.character(x)
[1] "1" "2" "3" "4" "5"

判断有几个水平

> nlevels(my_fac6)
[1] 4
> levels(my_fac6)
[1] "A"  "AB" "B"  "O" 

分类变量转换为哑变量

> my_fac7 <- relevel(my_fac6, ref="B")
#ref=reference
> my_fac7
[1] A  B  AB O 
Levels: B A AB O
> my_fac6
[1] A  B  AB O 
Levels: A AB B O

因子命名排序及其校正

> x <- c("placebo","10mg","20mg","50mg")
> my_order_fac <- factor(x,ordered = TRUE)
> my_order_fac 
[1] placebo 10mg    20mg    50mg   
Levels: 10mg < 20mg < 50mg < placebo
#解决方案
> x <- c("0mg","10mg","20mg","50mg")
> my_order_fac <- factor(x,ordered = TRUE)
> my_order_fac 
[1] 0mg  10mg 20mg 50mg
Levels: 0mg < 10mg < 20mg < 50mg
#或者是使用package desctools
> x <- c('P', '10mg', '20mg', '50mg')  
>  my_order_fac <- factor(x, ordered = TRUE)
>  library(DescTools)
>  my_order_fac2 <- reorder.factor(my_order_fac, new.order = x)
>  my_order_fac2
[1] P    10mg 20mg 50mg
Levels: P < 10mg < 20mg < 50mg

列表与矩阵

> my_list <- list(1,2,3,"R","nihaooo",TRUE,FALSE)
> my_list
[[1]]
[1] 1

[[2]]
[1] 2

[[3]]
[1] 3

[[4]]
[1] "R"

[[5]]
[1] "nihaooo"

[[6]]
[1] TRUE

[[7]]
[1] FALSE

>  my_list2 <- list(1:10,letters[1:5])
> my_list2
[[1]]
 [1]  1  2  3  4  5  6  7  8  9 10

[[2]]
[1] "a" "b" "c" "d" "e"
#多种数据类型的列表

> my_list2[[2]]
[1] "a" "b" "c" "d" "e"
> my_list2[[2]][1]
[1] "a"
#列表的定位

> my_list3 <- list(1:10,letters[1:5],list(11:14,LETTERS[1:5]))
> my_list3 
[[1]]
 [1]  1  2  3  4  5  6  7  8  9 10

[[2]]
[1] "a" "b" "c" "d" "e"

[[3]]
[[3]][[1]]
[1] 11 12 13 14

[[3]][[2]]
[1] "A" "B" "C" "D" "E"

> my_list3[[3]][[2]][1]
[1] "A"
#列表的相应元素的定位

矩阵

>  my_matrix <- matrix(data = 1:6,nrow = 2,byrow = TRUE)
> my_matrix
     [,1] [,2] [,3]
[1,]    1    2    3
[2,]    4    5    6
#nrow:行数，byrow默认是FALSE，默认按列排序
> my_matrix2 <- matrix(data = 1:10, nrow = 5)
> my_matrix2 
     [,1] [,2]
[1,]    1    6
[2,]    2    7
[3,]    3    8
[4,]    4    9
[5,]    5   10
> my_matrix3 <- matrix(data = 2, nrow = 3,ncol=4)
> my_matrix3
     [,1] [,2] [,3] [,4]
[1,]    2    2    2    2
[2,]    2    2    2    2
[3,]    2    2    2    2
> my_matrix4 <- matrix(data =letters[1:3], nrow = 2,ncol=4)
#Warning message:
#In matrix(data = letters[1:3], nrow = 2, ncol = 4) :
  #数据长度[3]不是矩阵行数[2]的整倍
  #该位置只报警告但是仍然出矩阵
> my_matrix4 
     [,1] [,2] [,3] [,4]
[1,] "a"  "c"  "b"  "a" 
[2,] "b"  "a"  "c"  "b" 

>  my_matrix5 <- matrix(data = 1:12, nrow = 3, ncol = 4, 
+                       dimnames = list(c('A','B','C'),c('V1','V2','V3','V4')))
>  my_matrix5
  V1 V2 V3 V4
A  1  4  7 10
B  2  5  8 11

> t(my_matrix5)#转置
    A  B  C
V1  1  2  3
V2  4  5  6
V3  7  8  9
V4 10 11 12

> my_matrix6 <- matrix(data=c(1:6,letters[1:6]), nrow = 3, ncol = 4)
> my_matrix6
     [,1] [,2] [,3] [,4]
[1,] "1"  "4"  "a"  "d" 
[2,] "2"  "5"  "b"  "e" 
[3,] "3"  "6"  "c"  "f" 

数组是多维的矩阵

> dim(my_array)
[1] 2 4 2
> dim(my_array) <- c(4,2,2)
> mny_array 
, , 1

     [,1] [,2] [,3] [,4]
[1,]    1    3    5    7
[2,]    2    4    6    8

, , 2

     [,1] [,2] [,3] [,4]
[1,]    9   11   13   15
[2,]   10   12   14   16
#改变相关维度

#命名
> my_array2 <- array(1:16, dim = c(4,2,2), dimnames = list(c(LETTERS[1:4]),c('col1','col2'),c('first','second')))
> my_array2
, , first

  col1 col2
A    1    5
B    2    6
C    3    7
D    4    8

, , second

  col1 col2
A    9   13
B   10   14
C   11   15
D   12   16

#相关位置的数值提取
> my_matrix 
     [,1] [,2]
[1,]    1    5
[2,]    2    6
[3,]    3    7
[4,]    4    8
> my_matrix [4,2]
[1] 8
> my_matrix[3,]
[1] 3 7
> my_matrix[,1]
[1] 1 2 3 4
> my_array2[2,2,1]
[1] 6
> my_array2[,2,1]
A B C D 
5 6 7 8 

数据框

> my_df <- data.frame(name=c('TOM','ENDY','MARRY'),age=c(24,25,26),height=c(15,20,30))
> my_df
   name age height
1   TOM  24     15
2  ENDY  25     20
3 MARRY  26     30
#命名时，数字加英语不合法，纯数字不合法，带有特殊字符不合法，！下划线合法！
#大小写是区别的

> dim(my_df)
[1] 3 3
> View(my_df)
#可以看得到数据的表格样式